{"id":"https://openalex.org/W4415792814","doi":"https://doi.org/10.1007/978-981-95-1021-4_35","title":"Lembda: Optimizing LLM Inference on\u00a0Embedded Platforms via\u00a0CPU/FPGA Co-processing","display_name":"Lembda: Optimizing LLM Inference on\u00a0Embedded Platforms via\u00a0CPU/FPGA Co-processing","publication_year":2025,"publication_date":"2025-11-03","ids":{"openalex":"https://openalex.org/W4415792814","doi":"https://doi.org/10.1007/978-981-95-1021-4_35"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-95-1021-4_35","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-1021-4_35","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109419352","display_name":"Jinwei Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I70908550","display_name":"Anhui Polytechnic University","ror":"https://ror.org/041sj0284","country_code":"CN","type":"education","lineage":["https://openalex.org/I70908550"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinwei Zhou","raw_affiliation_strings":["The Anhui Engineering Research Center of Vehicle Display Integrated Systems, Joint Discipline Key Laboratory of Touch Display Materials and Devices, School of Integrated Circuits, Anhui Polytechnic University, Wuhu, 241000, China"],"affiliations":[{"raw_affiliation_string":"The Anhui Engineering Research Center of Vehicle Display Integrated Systems, Joint Discipline Key Laboratory of Touch Display Materials and Devices, School of Integrated Circuits, Anhui Polytechnic University, Wuhu, 241000, China","institution_ids":["https://openalex.org/I70908550"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104100813","display_name":"Chenhao Xue","orcid":"https://orcid.org/0000-0001-9721-247X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenhao Xue","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020237745","display_name":"Xiping Dong","orcid":"https://orcid.org/0009-0001-8720-5804"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiping Dong","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101717774","display_name":"Yi Ren","orcid":"https://orcid.org/0009-0001-8759-6585"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":["School of Software and Microelectronics, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628339","display_name":"Jiaxing Zhang","orcid":"https://orcid.org/0000-0003-4104-6657"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxing Zhang","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850376","display_name":"Guangyu Sun","orcid":"https://orcid.org/0000-0001-6436-0820"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Sun","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108077980","display_name":"Xinnan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I70908550","display_name":"Anhui Polytechnic University","ror":"https://ror.org/041sj0284","country_code":"CN","type":"education","lineage":["https://openalex.org/I70908550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinnan Lin","raw_affiliation_strings":["The Anhui Engineering Research Center of Vehicle Display Integrated Systems, Joint Discipline Key Laboratory of Touch Display Materials and Devices, School of Integrated Circuits, Anhui Polytechnic University, Wuhu, 241000, China"],"affiliations":[{"raw_affiliation_string":"The Anhui Engineering Research Center of Vehicle Display Integrated Systems, Joint Discipline Key Laboratory of Touch Display Materials and Devices, School of Integrated Circuits, Anhui Polytechnic University, Wuhu, 241000, China","institution_ids":["https://openalex.org/I70908550"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5109419352"],"corresponding_institution_ids":["https://openalex.org/I70908550"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53702942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"426","last_page":"431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3937999904155731,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3937999904155731,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.10540000349283218,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.06989999860525131,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7389000058174133},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7031999826431274},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6894999742507935},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5968000292778015},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4948999881744385},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4828000068664551},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.4611999988555908},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4478999972343445},{"id":"https://openalex.org/keywords/reconfigurable-computing","display_name":"Reconfigurable computing","score":0.41200000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8955000042915344},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7389000058174133},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7031999826431274},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6894999742507935},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5968000292778015},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4885999858379364},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4828000068664551},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.4611999988555908},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.41200000047683716},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.37959998846054077},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.3546000123023987},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C206274596","wikidata":"https://www.wikidata.org/wiki/Q1063837","display_name":"Programmable logic device","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-95-1021-4_35","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-1021-4_35","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2137269967","https://openalex.org/W3137147200","https://openalex.org/W4404783742","https://openalex.org/W4406458045"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-11-03T00:00:00"}
